OpenRouter LLM API pricing

Every model OpenRouter serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first. Verified against LiteLLM and OpenRouter daily.

Models served

475

on this provider

Cheapest input

$0.00

per 1M tokens

Cheapest output

$0.00

per 1M tokens

Max context

2M

tokens

Model ID
Qwen3 Next 80B A3B Instruct (free)Alibaba262K$0.00$0.00qwen/qwen3-next-80b-a3b-instruct:free
Qwen3 Coder 480B A35B (free)Alibaba1M$0.00$0.00qwen/qwen3-coder:free
Uncensored (free)Mistral33K$0.00$0.00cognitivecomputations/dolphin-mistral-24b-venice-edition:free
Llama 3.3 70B Instruct (free)Meta131K$0.00$0.00meta-llama/llama-3.3-70b-instruct:free
Llama 3.2 3B Instruct (free)Meta131K$0.00$0.00meta-llama/llama-3.2-3b-instruct:free
Hermes 3 405B Instruct (free)Nous Research131K$0.00$0.00nousresearch/hermes-3-llama-3.1-405b:free
Ling-3.0-flash (free)Other262K$0.00$0.00inclusionai/ling-3.0-flash:free
MiniMax M3 (free)MiniMax1M$0.00$0.00minimax/minimax-m3:free
Ling 3.0 Flash Fin (free)Other262K$0.00$0.00inclusionai/ling-3.0-flash-fin:free
Inkling Small (free)Other1M$0.00$0.00thinkingmachines/inkling-small:free
Inkling (free)Other1M$0.00$0.00thinkingmachines/inkling:free
GLM 5.2 (free)Zhipu256K$0.00$0.00z-ai/glm-5.2:free
Dots3-Note Preview (free)Other512K$0.00$0.00dots-studio/dots-3-note-preview:free
Nemotron 3.5 Lightning (free)NVIDIA1M$0.00$0.00nvidia/nemotron-3.5-lightning:free
LFM2.5-2.6B (free)Liquid AI66K$0.00$0.00liquid/lfm-2.5-2.6b:free
Nemotron 3.5 Content Safety (free)NVIDIA128K$0.00$0.00nvidia/nemotron-3.5-content-safety:free
Nemotron 3 Ultra (free)NVIDIA1M$0.00$0.00nvidia/nemotron-3-ultra-550b-a55b:free
Body Builder (beta)Other128K$0.00$0.00openrouter/openrouter/bodybuilder
Hy3 (free)Other262K$0.00$0.00tencent/hy3:free
North Mini Code (free)Cohere256K$0.00$0.00cohere/north-mini-code:free
Laguna M.1 (free)Other262K$0.00$0.00poolside/laguna-m.1:free
Ling 3.0 Tiny (free)Other262K$0.00$0.00inclusionai/ling-3.0-tiny:free
Ox AlphaOther1M$0.00$0.00stealth/ox-alpha
Nemotron Nano 12B 2 VL (free)NVIDIA128K$0.00$0.00nvidia/nemotron-nano-12b-v2-vl:free
Nemotron 3 Nano 30B A3B (free)NVIDIA256K$0.00$0.00nvidia/nemotron-3-nano-30b-a3b:free
Nemotron Nano 9B V2 (free)NVIDIA128K$0.00$0.00nvidia/nemotron-nano-9b-v2:free
Nemotron 3 Nano Omni (free)NVIDIA256K$0.00$0.00nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
Laguna XS 2.1 (free)Other262K$0.00$0.00poolside/laguna-xs-2.1:free
Laguna S 2.1 (free)Other262K$0.00$0.00poolside/laguna-s-2.1:free
MiniMax M2.7 (free)MiniMax197K$0.00$0.00minimax/minimax-m2.7:free
Gemma 4 31B (free)Google262K$0.00$0.00google/gemma-4-31b-it:free
Gemma 4 26B A4B (free)Google262K$0.00$0.00google/gemma-4-26b-a4b-it:free
Lyria 3 Pro PreviewGoogle131K$0.00$0.00google/lyria-3-pro-preview
Lyria 3 Clip PreviewGoogle131K$0.00$0.00google/lyria-3-clip-preview
Nemotron 3 Super (free)NVIDIA262K$0.00$0.00nvidia/nemotron-3-super-120b-a12b:free
gpt-oss-20b (free)OpenAI131K$0.00$0.00openai/gpt-oss-20b:free
Ling-2.6-flashOther262K$0.01$0.03inclusionai/ling-2.6-flash
Granite 4.0 MicroIBM131K$0.02$0.11ibm-granite/granite-4.0-h-micro
Mistral NemoMistral131K$0.02$0.03mistralai/mistral-nemo
Ling-3.0-flashOther262K$0.02$0.06inclusionai/ling-3.0-flash
GPT-5 Nano (batch)OpenAI400K$0.03$0.20openai/gpt-5-nano:batch
Nex-N2-MiniOther262K$0.03$0.10nex-agi/nex-n2-mini
Llama 3.2 1B InstructMeta131K$0.03$0.20meta-llama/llama-3.2-1b-instruct
DeepSeek V4 Flash LatestDeepSeek1.3M$0.03$0.10~deepseek/deepseek-v4-flash-latest
Solar Pro 4Other524K$0.03$0.12upstage/solar-pro4
Qwen3.7 FlashAlibaba1M$0.03$0.13qwen/qwen3.7-flash
gpt-oss-20bOpenAI131K$0.03$0.13openai/gpt-oss-20b
Nova Micro 1.0Amazon128K$0.04$0.14amazon/nova-micro-v1
gpt-oss-120bOpenAI131K$0.04$0.17openai/gpt-oss-120b
Command R7B (12-2024)Cohere128K$0.04$0.15cohere/command-r7b-12-2024
150 of 475
Page 1 of 10
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI